| 主权项 |
1. A system for a dynamically evolving cognitive architecture planning, the system comprising:
one or more processors; and a non-transitory computer readable medium storing a plurality of instructions, which when executed, cause the one or more processors to: form an intent based on a user input; create a first plan based on the intent, wherein the first plan comprises a first action object that transforms a first concept object associated with the intent into a second concept object and comprises a second action object that transforms the second concept object into a third concept object associated with a goal of the intent, wherein the first action object and the second action object are selected from a plurality of action objects; create a second plan based on the intent, wherein the second plan comprises a third action object that transforms the first concept object associated with the intent into a fourth concept object and comprises a fourth action object that transforms the fourth concept object into the third concept object associated with the goal of the intent, wherein the third action object and the fourth action object are selected from the plurality of action objects; select the first plan for execution based on comparison of the first plan to the second plan based on at least one of an action object cost, an action object quality, and a number of planned action objects; execute the first plan, and output a value associated with the third concept object. |
